MAE Seminar: Mechanics-data coupling for intelligent diagnosis and prognosis of battery energy system

Details

MAE Seminar: Mechanics-data coupling for intelligent diagnosis and prognosis of battery energy system
Date: March 10, 2026
Time: 12:50 PM Location: MAE-A 303

Dr. Yunhong Che
Research Fellow, Massachusetts Institute of Technology
Assistant Professor, Aalborg University

Abstract
Accurate and reliable state and thermal monitoring, health and fault diagnosis, and lifetime prediction are critical to ensure the safe operation of batteries in energy storage systems. Factors such as different battery types, varying battery pack topologies, diverse user scenarios, and regional characteristics contribute to significant pattern differences, thus challenging optimal management. Integrating artificial intelligence technologies has brought new opportunities for the intelligent management of batteries. However, existing battery system management still faces challenges such as low model reliability, poor generalization capability, and weak mechanistic interpretability. This seminar will introduce advanced learning strategies and hybrid modeling approaches to enhance battery monitoring and health assessment. Systematic modeling for battery system health evaluation, advanced transfer learning strategies, and physics-data coupling strategies, including mechanism-guided residual compensation and mechanistically constrained machine learning, will be introduced. These approaches support monitoring at both the cell scale (state, temperature, and fault signatures) and the electrode scale (interpretable degradation modes and latent health states), providing actionable insights for control and decision-making. This seminar highlights the combination of mechanistic information and machine learning for enhanced battery diagnosis and prognosis to improve accuracy, reliability, and interpretability in intelligent battery management.

Biography
Yunhong Che received the Ph.D. degree in Energy Technology from Aalborg University, Denmark, in 2024. He previously received the B.E. and M.S. degrees in Automotive Engineering from Chongqing University, China, in 2019 and 2021. He was a visiting student researcher with the Swiss Federal Institute of Technology in Lausanne (EPFL), Switzerland, and Stanford University, USA, from April 2023 to December 2023.
He is currently a Research Fellow with the Department of Chemical Engineering, Massachusetts Institute of Technology, USA, where he was a postdoc from 2024 to 2025, and an Assistant Professor with the Department of Energy, Aalborg University, Denmark (joint employment). He is the associate editor of IEEE Transactions on Industrial Informatics and a recipient of several best paper awards. His research interests include intelligent diagnosis and prognosis, AI for science, data-physics coupled battery modeling and monitoring, and energy system control and optimization.

Faculty Host: Dr. Nam Ho Kim